{"total":18,"rows":[{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2503.19612","title":"RL-finetuning LLMs from on- and off-policy data with a single algorithm","created":"2025-03-25","cited_by_count":11,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2406.12221","title":"On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation","created":"2024-06-18","cited_by_count":9,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2603.06748","title":"Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2412.20340","title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","created":"2024-12-29","cited_by_count":2,"area":null},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2605.19033","title":"RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2603.01973","title":"CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.12192","title":"How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.04141","title":"Efficient Test-Time Adaptation through Human-AI Interaction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.02051","title":"Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}